4 papers
2D or 3D: Who Governs Salience in VLA Models? -- Tri-Stage Token Pruning Framework with Modality Salience Awareness
Zihao Zheng, Sicheng Tian, Zhihao Mao +8
Vision-Language-Action (VLA) models have emerged as the mainstream of embodied intelligence. Recent VLA models have expanded their input modalities from 2D-only to 2D+3D paradigms,…
OmniGround: A Comprehensive Spatio-Temporal Grounding Benchmark for Real-World Complex Scenarios
Hong Gao, Jingyu Wu, Xiangkai Xu +5
Spatio-Temporal Video Grounding (STVG) aims to localize target objects in videos based on natural language descriptions. Despite recent advances in Multimodal Large Language Models…
Agentic Video Intelligence: A Flexible Framework for Advanced Video Exploration and Understanding
Hong Gao, Yiming Bao, Xuezhen Tu +6
Video understanding requires not only visual recognition but also complex reasoning. While Vision-Language Models (VLMs) demonstrate impressive capabilities, they typically process…
APVR: Hour-Level Long Video Understanding with Adaptive Pivot Visual Information Retrieval
Hong Gao, Yiming Bao, Xuezhen Tu +3
Current multimodal large language models (MLLMs) struggle with hour-level video understanding, facing significant challenges not only in modeling the substantial information volume…